Language Models
ictnlp/LLaVA-Mini
LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.
PythonApache-2.0updated Jun 29, 2025
LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills
$ git clone https://github.com/LLaVA-VL/LLaVA-Plus-Codebase.gitLLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.
Paper collection on building and evaluating language model agents via executable language grounding
[EMNLP 2026] OceanGym: A Benchmark Environment for Underwater Embodied Agents
▲ +117 ★ this week
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
▲ +592 ★ this week
《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码
▲ +429 ★ this week
Build and run agents you can see, understand and trust.
Data from GitHub · snapshot Nov 13, 2026